Face hallucination via weighted sparse representation

Zhongyuan Wang, Junjun Jiang, Zixiang Xiong, Ruimin Hu, Zhenfeng Shao

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

5 Citations (Scopus)


By incorporating the priors of image positions, position-patch based face hallucination methods can produce high-quality results and save computation time. These methods represent the test image patch as a linear combination of the same position patches in a training dictionary, and the key issue is how to obtain the optimal coefficients. Due to stability and accuracy issues, methods based on least square estimation or sparse representation (SR) proposed so far are not satisfactory. In this paper, we improve existing SR methods by exploiting similarity between the test and training patches. In particular, we impose a similarity constraint (in terms of the distance between the test patch and bases in the dictionary) on the ℓ1 minimization regularization term and obtain the coefficients by solving a weighted SR problem. We also provide a new prospective on weighted SR and investigate its robustness to illumination variations. Experiments on commonly used database demonstrate that our method outperforms state of the art.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages4
ISBN (Print)9781479903566
Publication statusPublished - 18 Oct 2013
Externally publishedYes
EventIEEE International Conference on Acoustics, Speech and Signal Processing 2013 - Vancouver Convention Center, Vancouver, Canada
Duration: 26 May 201331 May 2013
http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6619549 (Conference Proceedings)


ConferenceIEEE International Conference on Acoustics, Speech and Signal Processing 2013
Abbreviated titleICASSP 2013
Internet address


  • face hallucination
  • position patches
  • Super-resolution
  • weighted sparse representation

Cite this